© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13139
    Prev
    Next
    INDEX
    Explanations

    ingredients:at toI wethe ladiesmajor componenta televised2 0

    np_acts-logits-general · gemini-2.5-flash-lite

    purpose, privacy, environmental impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PAOK
    0.50
    ⒈
    0.48
    펴
    0.47
     Aplic
    0.46
     く
    0.46
     approxim
    0.46
    <bbox>
    0.45
    ्ज
    0.45
     남
    0.45
    ateurs
    0.45
    POSITIVE LOGITS
     当然
    0.43
    ̘
    0.42
    ীদ
    0.42
     greenish
    0.41
     AID
    0.41
     sommige
    0.41
     vissa
    0.41
     synergistic
    0.40
     chad
    0.39
     =\
    0.39
    Activations Density 0.000%

    No Known Activations